You will work inside the company's frontline business units as a senior forward deployed AI engineer, tackling the hardest, least defined operational problems where the stakes are high.
You own the technical direction from start to finish, designing and shipping production agentic systems, retrieval-augmented generation (RAG) engines, full-stack microservices, and decision tools that run live operations.
You combine strong engineering with a product view. You will build custom orchestration layers with LangGraph, Temporal, or hand-built state machines, set context management rules that scale, and run workloads on Domino, Airflow, and Kubernetes. Your one-off builds should become shared SDKs, libraries, and playbooks used across the company.
Responsibilities
Design the full-stack architecture for embedded AI and agent work, covering multi-agent orchestration, state machines, latency and cost budgets, security boundaries, and back-end integration.
Build stateful agent workflows that follow the company's agentic governance rules, using LangGraph, Temporal, or event-driven state machines. Set strict controls for tool calls, execution sandboxing, and deterministic fallbacks.
Lead the design of production RAG systems with hybrid search, re-ranking, metadata filters, and semantic caching, shaping and scaling the company's context architecture.
Ship production agent services and scheduled jobs to runtimes such as Domino Data Lab, Apache Airflow, Kubernetes microservices, and serverless compute on AWS, GCP, or Azure.
Build offline and online evaluation frameworks, including LLM-as-a-judge, synthetic test generation, human review queues, and live A/B rollouts, to track model drift, hallucination rates, and task completion.
Turn custom deployments into reusable internal SDKs, API building blocks, and modular UI components. Mentor engineers across the organization and write technical documentation for patent disclosures.
Work alongside business unit leaders to map complex operational processes, cut through the noise, and find where applied AI will deliver measurable gains.
Act as the technical authority with business unit vice presidents and managing directors, explaining model behavior, failure modes, and performance trade-offs in plain terms.
Requirements
A bachelor's degree in computer science, software engineering, or a related technical field, or 4+ years of work experience.
8+ years of relevant experience, which may come from work, military service, specialized training, or a mix of these.
Hands-on experience with frontier LLMs such as Anthropic Claude, OpenAI, and Google Gemini, plus agentic developer tools like Claude Code, Cursor, and Copilot, used to deliver scalable solutions and hit core business goals.
8+ years shipping production software, and/or proven experience putting LLM applications, agent workflows, or autonomous tool-calling pipelines into production.
Strong Python and modern TypeScript/Node.js skills for full-stack API work and back-end orchestration.
Experience with Docker containers, API design, and AWS, GCP, or Azure.
A record of building offline evaluation benchmarks and online evaluation and observability pipelines covering latency, token cost, hallucination tracking, and eval-driven development.
Deep knowledge of retrieval and context design: production RAG pipelines, vector databases such as pgvector, Milvus, or Pinecone, hybrid dense and sparse/lexical search, and dynamic context management.
Proven experience deploying containerized services and data workflows on platforms like Domino Data Lab, Apache Airflow, and Kubernetes (EKS/GKE), plus hyperscaler clouds.
Advanced full-stack skills in Python, SQL, and modern JavaScript/TypeScript.
A track record designing offline and online eval harnesses, guardrail frameworks, and observability systems covering latency, token optimization, and tracing.
Ability to scope ambiguous technical work on your own and present architecture to senior executives.
Ability to work directly with enterprise stakeholders, turn vague business needs into technical architecture, and deliver projects end to end.
Even better: a master's degree in computer science, machine learning, robotics, or a related technical field.
Even better: experience building and scaling centralized context platforms or enterprise search, similar to the company's internal enterprise context layer platforms.
Even better: past forward-deployed engineering, solutions architecture, or technical consulting work at top-tier technology firms or hyperscalers.
Even better: a history of turning one-off operational builds into company-wide shared libraries, with technical publications or filed patents.
Even better: domain knowledge in telecommunications, customer growth and retention, customer segmentation, or large-scale customer care operations.
Candidates who do not meet every "even better" item are still encouraged to apply.
Conditions
Hybrid role with a set work location that includes working from home and at least 3 days per week in the office, assigned by your manager.
You are responsible for following the hybrid work policies.
Scheduled hours: 40 per week.
Pay varies by location and by confirmed job-related skills and experience.
This is an incentive-based role with potential to earn more.
Part-time pay is adjusted to match hours worked.
Full-time salary range for the listed location(s): $137,000.00 - $263,000.00.
Benefits
Medical, dental, and vision coverage, short- and long-term disability, basic and supplemental life insurance, AD&D insurance, identity theft protection, pet insurance, and group home and auto insurance.
Matched 401(k) savings plan.
Up to 8 paid company holidays per year and up to 6 personal days per year.
Paid parental leave, adoption assistance, and tuition assistance, plus other incentives.
Premium pay, depending on the role, such as overtime, shift differential, holiday pay, and allowances.
New hires receive up to 15 days of vacation per year, increasing with service.
Part-time benefit coverage varies, as some benefits depend on individual circumstances.